Visualizations Project

by: Anastasiia Tananaiska

from IPython.display import HTML
import pandas as pd
import altair as alt
import geopandas as gpd
import pycountry
import numpy as np
import os

alt.data_transformers.disable_max_rows()

DataTransformerRegistry.enable('default')

About Data

My dataset contains some of the major songs attributes (like acousticness, loudness, danceability, energy, etc) that describe certain songs from years 1960's up to 2010's (there's an equal division of hit songs and non-hit ones) therefore I decided to build the analysis mostly on that data. Besides that I also added the info about release dates, genres and country of artist's origin.

Merging Data

path = "data-parsed/"
files = [path + f for f in os.listdir(path) if "dataset" in f]

initial_dataset = pd.DataFrame()
for f in files:
    tmp = pd.read_csv(f)
    tmp = tmp.drop(tmp.columns[0], axis=1)
    years = {"00s": 2010, "10s": 2020, "60s": 1970, "70s": 1980, "80s": 1990, "90s": 2000}
    decade = f.split(".")[-2][-3:]
    tmp["decade"] = years[decade]
    initial_dataset = pd.concat([initial_dataset, tmp], ignore_index=True)

Cleaning and preparing data

initial_dataset.dropna(inplace=True)
initial_dataset = initial_dataset[initial_dataset["target"] == 1]

initial_dataset.columns

Index(['track', 'artist', 'uri', 'danceability', 'energy', 'key', 'loudness',
       'mode', 'speechiness', 'acousticness', 'instrumentalness', 'liveness',
       'valence', 'tempo', 'duration_ms', 'time_signature', 'chorus_hit',
       'sections', 'target', 'country', 'country_code', 'release_date',
       'style', 'genre', 'decade'],
      dtype='object')

initial_dataset.describe()

	danceability	energy	key	loudness	mode	speechiness	acousticness	instrumentalness	liveness	valence	tempo	duration_ms	time_signature	chorus_hit	sections	target	release_date	decade
count	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9286.000000	9.286000e+03	9286.000000	9286.000000	9286.000000	9286.0	9286.000000	9286.000000
mean	0.590372	0.641361	5.168210	-8.594532	0.730993	0.059157	0.246335	0.025553	0.188248	0.596081	121.052062	2.365007e+05	3.950355	39.439935	10.484385	1.0	1928.683287	1993.964032
std	0.145936	0.201670	3.545462	3.619409	0.443468	0.060647	0.257790	0.109918	0.160314	0.237670	27.367421	6.380371e+04	0.266636	17.578066	2.867590	0.0	349.675196	15.857415
min	0.000000	0.020400	0.000000	-27.010000	0.000000	0.000000	0.000002	0.000000	0.013600	0.000000	0.000000	5.938700e+04	0.000000	13.307160	3.000000	1.0	0.000000	1970.000000
25%	0.497000	0.498000	2.000000	-10.943750	0.000000	0.031300	0.033825	0.000000	0.087400	0.407000	100.312000	1.975065e+05	4.000000	27.657350	9.000000	1.0	1979.000000	1980.000000
50%	0.598000	0.663000	5.000000	-8.086000	1.000000	0.038500	0.144000	0.000011	0.126000	0.616000	119.619000	2.304335e+05	4.000000	35.593610	10.000000	1.0	1992.000000	1990.000000
75%	0.692000	0.805000	8.000000	-5.775250	1.000000	0.056900	0.402000	0.000745	0.244000	0.794000	136.232000	2.662008e+05	4.000000	46.327618	12.000000	1.0	2004.000000	2010.000000
max	0.988000	0.996000	11.000000	-0.716000	1.000000	0.941000	0.994000	0.982000	0.999000	0.985000	217.396000	1.367093e+06	5.000000	262.615400	55.000000	1.0	2020.000000	2020.000000

initial_dataset["index"] = initial_dataset.index
factors = initial_dataset[["index", "target", "decade", "energy", "danceability", "acousticness", "speechiness", "liveness"]]
factors = factors.melt(['index', "target", "decade"])

factors.columns

Index(['index', 'target', 'decade', 'variable', 'value'], dtype='object')

Visualization #1

For the first visual I'm exploring the distribution of the song features for each year, for both hits and non-hits songs.

I found out that the most appropriate visual type would be the box-plot as it allows to represent both statistical and visual info for each of the feature fields.

Advantages: easy to describe the distribution of the desired variables Disadvantages: restrictions in the interactivity, can't apply the selection. In my case that was not a major problem as there wasn't much years

alt.Chart(factors).mark_boxplot(extent="min-max")\
   .encode(x=alt.X("decade:O", title="Years"), 
            y=alt.Y("value:Q", title="Value"),
            color=alt.Color("count(value)", scale=alt.Scale(scheme='purples'), legend=None),
            column=alt.Column('variable:N', title="Feature"))\
   .properties(width=220, height=220, title="Feature values distribution for hit songs")

Visualization #2

Second insight - is the exploration of the distribution of top hits accross the available countries through years 1960's - 2010's.

Here I'm using the map with the slider that allows us to choose the year of interest.

slider = alt.binding_range(min=1970, max=2020, step=10)
selector = alt.selection_single(name="decade", fields=['decade'],
                                bind=slider, init={'decade': 1970})

keys = alt.Chart(initial_dataset)\
        .add_selection(selector)\
        .transform_filter(selector)\
        .transform_joinaggregate(song_counter='count()')\
        .transform_calculate(songs_percentage="1 / datum.song_counter")\
        .mark_bar()\
        .encode(x=alt.X("key:O", title="ID of the key", axis=alt.Axis(labelAngle=360)),
                y=alt.Y('sum(songs_percentage):Q', title="No. of songs", axis=alt.Axis(format="%")),
                color=alt.Color("sum(songs_percentage):Q", scale=alt.Scale(scheme='purples'), legend=None),
                tooltip=[alt.Tooltip("key", title="ID of the key"),
                         alt.Tooltip('count()', title='No. of songs'),
                         alt.Tooltip("sum(songs_percentage):Q", title="Percentage of the songs", format=".1%")])\
        .properties(width=600, height=400, title="Most common song keys through the years, %")


styles = alt.Chart(initial_dataset)\
            .add_selection(selector)\
            .transform_filter(selector)\
            .transform_joinaggregate(song_counter2='count()')\
            .transform_calculate(songs_percentages="1 / datum.song_counter2")\
            .mark_bar()\
            .encode(x=alt.X("style:O", title="\nStyle", axis=alt.Axis(labelAngle=360),
                          sort=alt.EncodingSortField(field="style", op="count", order='descending')),
                    y=alt.Y('sum(songs_percentages):Q', title="No. of songs", axis=alt.Axis(format="%")),
                    color=alt.Color("sum(songs_percentages):Q", scale=alt.Scale(scheme='purples'), legend=None),
                    tooltip=[alt.Tooltip("style", title="Style of the song"),
                             alt.Tooltip("count()", title="No. of songs"),
                             alt.Tooltip("sum(songs_percentages):Q", title="Percentage of the songs", format=".1%")])\
        .properties(width=600, height=400, title="Most common song styles through the years, %")
        
concc=alt.hconcat(keys, styles, center=True).configure_concat(spacing=10).resolve_scale(color='independent')

display(HTML("""
<style>
.vega-bind {
  text-align:center;
}
</style>
"""))

display(concc)

Visualization #3

world = gpd.read_file("world-countries.json")
world.id.unique()

array(['AFG', 'AGO', 'ALB', 'ARE', 'ARG', 'ARM', 'ATA', 'ATF', 'AUS',
       'AUT', 'AZE', 'BDI', 'BEL', 'BEN', 'BFA', 'BGD', 'BGR', 'BHS',
       'BIH', 'BLR', 'BLZ', 'BOL', 'BRA', 'BRN', 'BTN', 'BWA', 'CAF',
       'CAN', 'CHE', 'CHL', 'CHN', 'CIV', 'CMR', 'COD', 'COG', 'COL',
       'CRI', 'CUB', '-99', 'CYP', 'CZE', 'DEU', 'DJI', 'DNK', 'DOM',
       'DZA', 'ECU', 'EGY', 'ERI', 'ESP', 'EST', 'ETH', 'FIN', 'FJI',
       'FLK', 'FRA', 'GAB', 'GBR', 'GEO', 'GHA', 'GIN', 'GMB', 'GNB',
       'GNQ', 'GRC', 'GRL', 'GTM', 'GUY', 'HND', 'HRV', 'HTI', 'HUN',
       'IDN', 'IND', 'IRL', 'IRN', 'IRQ', 'ISL', 'ISR', 'ITA', 'JAM',
       'JOR', 'JPN', 'KAZ', 'KEN', 'KGZ', 'KHM', 'KOR', 'KWT', 'LAO',
       'LBN', 'LBR', 'LBY', 'LKA', 'LSO', 'LTU', 'LUX', 'LVA', 'MAR',
       'MDA', 'MDG', 'MEX', 'MKD', 'MLI', 'MMR', 'MNE', 'MNG', 'MOZ',
       'MRT', 'MWI', 'MYS', 'NAM', 'NCL', 'NER', 'NGA', 'NIC', 'NLD',
       'NOR', 'NPL', 'NZL', 'OMN', 'PAK', 'PAN', 'PER', 'PHL', 'PNG',
       'POL', 'PRI', 'PRK', 'PRT', 'PRY', 'QAT', 'ROU', 'RUS', 'RWA',
       'SAU', 'SDN', 'SDS', 'SEN', 'SLB', 'SLE', 'SLV', 'SOM', 'SRB',
       'SUR', 'SVK', 'SVN', 'SWE', 'SWZ', 'SYR', 'TCD', 'TGO', 'THA',
       'TJK', 'TKM', 'TLS', 'TTO', 'TUN', 'TUR', 'TWN', 'TZA', 'UGA',
       'UKR', 'URY', 'USA', 'UZB', 'VEN', 'VNM', 'VUT', 'PSE', 'YEM',
       'ZAF', 'ZMB', 'ZWE'], dtype=object)

for index, row in initial_dataset.iterrows():
    location_ = row["country_code"]
    search_ = pycountry.countries.search_fuzzy(location_)
    initial_dataset.loc[index, "location"] = search_[0].alpha_3

merged = pd.merge(world, initial_dataset, how="outer", left_on="id", right_on="location")
merged

	id	name	geometry	track	artist	uri	danceability	energy	key	loudness	...	sections	target	country	country_code	release_date	style	genre	decade	index	location
0	AFG	Afghanistan	POLYGON ((61.21082 35.65007, 62.23065 35.27066...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	AGO	Angola	MULTIPOLYGON (((16.32653 -5.87747, 16.57318 -6...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	ALB	Albania	POLYGON ((20.59025 41.85540, 20.46317 41.51509...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	ARE	United Arab Emirates	POLYGON ((51.57952 24.24550, 51.75744 24.29407...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	ARG	Argentina	MULTIPOLYGON (((-65.50000 -55.20000, -66.45000...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9425	NaN	NaN	None	Pour It Up	Rihanna	spotify:track:76VtA90NKurNqaQpV126Ue	0.785	0.478	2.0	-8.735	...	8.0	1.0	Saint Michael, Barbados	BB	2012.0	Rock/Pop	Pop	2020.0	40235.0	BRB
9426	NaN	NaN	None	Rude Boy	Rihanna	spotify:track:60jzFy6Nn4M0iD1d94oteF	0.563	0.750	11.0	-4.496	...	9.0	1.0	Saint Michael, Barbados	BB	2009.0	Rock/Pop	Pop	2020.0	40397.0	BRB
9427	NaN	NaN	None	Impossible	Shontelle	spotify:track:45EDI3rk0f4cAMt9f8b56R	0.599	0.624	8.0	-3.631	...	11.0	1.0	Saint James, Barbados	BB	2010.0	Rock/Pop	R&B	2020.0	40481.0	BRB
9428	NaN	NaN	None	Love On The Brain	Rihanna	spotify:track:5oO3drDxtziYU2H1X23ZIp	0.509	0.637	4.0	-4.830	...	11.0	1.0	Saint Michael, Barbados	BB	2016.0	Rock/Pop	Pop	2020.0	40507.0	BRB
9429	NaN	NaN	None	What Now	Rihanna	spotify:track:0aUWfpD3PlSv3FTTKcT2rN	0.402	0.696	8.0	-4.799	...	11.0	1.0	Saint Michael, Barbados	BB	2012.0	Rock/Pop	Pop	2020.0	41097.0	BRB

9430 rows × 30 columns

filtered = merged.dropna().reset_index(drop=True).groupby(["name"]).count()["track"].reset_index()

filtered_ = pd.merge(merged, filtered, how="left", left_on="name", right_on="name")

filtered_

	id	name	geometry	track_x	artist	uri	danceability	energy	key	loudness	...	target	country	country_code	release_date	style	genre	decade	index	location	track_y
0	AFG	Afghanistan	POLYGON ((61.21082 35.65007, 62.23065 35.27066...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	AGO	Angola	MULTIPOLYGON (((16.32653 -5.87747, 16.57318 -6...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	ALB	Albania	POLYGON ((20.59025 41.85540, 20.46317 41.51509...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	ARE	United Arab Emirates	POLYGON ((51.57952 24.24550, 51.75744 24.29407...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	ARG	Argentina	MULTIPOLYGON (((-65.50000 -55.20000, -66.45000...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9425	NaN	NaN	None	Pour It Up	Rihanna	spotify:track:76VtA90NKurNqaQpV126Ue	0.785	0.478	2.0	-8.735	...	1.0	Saint Michael, Barbados	BB	2012.0	Rock/Pop	Pop	2020.0	40235.0	BRB	NaN
9426	NaN	NaN	None	Rude Boy	Rihanna	spotify:track:60jzFy6Nn4M0iD1d94oteF	0.563	0.750	11.0	-4.496	...	1.0	Saint Michael, Barbados	BB	2009.0	Rock/Pop	Pop	2020.0	40397.0	BRB	NaN
9427	NaN	NaN	None	Impossible	Shontelle	spotify:track:45EDI3rk0f4cAMt9f8b56R	0.599	0.624	8.0	-3.631	...	1.0	Saint James, Barbados	BB	2010.0	Rock/Pop	R&B	2020.0	40481.0	BRB	NaN
9428	NaN	NaN	None	Love On The Brain	Rihanna	spotify:track:5oO3drDxtziYU2H1X23ZIp	0.509	0.637	4.0	-4.830	...	1.0	Saint Michael, Barbados	BB	2016.0	Rock/Pop	Pop	2020.0	40507.0	BRB	NaN
9429	NaN	NaN	None	What Now	Rihanna	spotify:track:0aUWfpD3PlSv3FTTKcT2rN	0.402	0.696	8.0	-4.799	...	1.0	Saint Michael, Barbados	BB	2012.0	Rock/Pop	Pop	2020.0	41097.0	BRB	NaN

9430 rows × 31 columns